Structured Diffusion Processes in Deep Generative Models
Diffusion generative models have emerged as a powerful, versatile, and elegant generative modeling framework for diverse data modalities. However, the high computational cost of inference relative to other frameworks remains a chief limitation of such models. At the same time, the design space of a...
Main Author: | Jing, Bowen |
---|---|
Other Authors: | Jaakkola, Tommi |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/147277 |
Similar Items
-
Second generation diffusion model of interacting gravity waves on the surface of deep fluid
by: A. Pushkarev, et al.
Published: (2004-01-01) -
End-to-end protein–ligand complex structure generation with diffusion-based generative models
by: Shuya Nakata, et al.
Published: (2023-06-01) -
Deep generative models for natural language processing
by: Miao, Y
Published: (2017) -
Diffusion probabilistic models enhance variational autoencoder for crystal structure generative modeling
by: Teerachote Pakornchote, et al.
Published: (2024-01-01) -
Robustness, structure and hierarchy in deep generative models
by: Willetts, MJF
Published: (2021)